CN117333945B - Snake running motion detection method, device, equipment and storage medium - Google Patents
Snake running motion detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117333945B CN117333945B CN202311336864.6A CN202311336864A CN117333945B CN 117333945 B CN117333945 B CN 117333945B CN 202311336864 A CN202311336864 A CN 202311336864A CN 117333945 B CN117333945 B CN 117333945B
- Authority
- CN
- China
- Prior art keywords
- motion
- pole
- area
- field
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000033001 locomotion Effects 0.000 title claims abstract description 218
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 241000270295 Serpentes Species 0.000 title description 4
- 239000003550 marker Substances 0.000 claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 36
- WYTGDNHDOZPMIW-RCBQFDQVSA-N alstonine Natural products C1=CC2=C3C=CC=CC3=NC2=C2N1C[C@H]1[C@H](C)OC=C(C(=O)OC)[C@H]1C2 WYTGDNHDOZPMIW-RCBQFDQVSA-N 0.000 claims abstract description 29
- 230000006399 behavior Effects 0.000 claims abstract description 22
- 238000010586 diagram Methods 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims abstract description 12
- 230000009466 transformation Effects 0.000 claims abstract description 10
- 230000037147 athletic performance Effects 0.000 claims abstract description 7
- 238000013459 approach Methods 0.000 claims description 7
- 230000000386 athletic effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims 2
- 230000003287 optical effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The present disclosure provides a serpentine running motion detection method, system, device and storage medium, wherein the method comprises: identifying a target on a field by adopting a target identification model, converting a field plane coordinate through perspective transformation according to the spatial position of the target to obtain a plane diagram corresponding to the field, calculating the range of an in-field area and an out-of-field area based on the plane diagram, and determining the target plane coordinate, wherein the in-field area comprises: a motion zone and a buffer zone; identifying the motion information by adopting a target identification model, determining the athlete, determining the relationship between the human pole in the motion range of the motion area and the buffer area corresponding to each marker pole, determining the current motion position and the marker pole state of the athlete, and judging the correctness of the relationship between the human pole according to the motion position; forming a motion sequence through a correct human pole relation, judging motion behaviors in each motion range based on the motion sequence and the marker pole state, and performing visual display; and drawing the motion trail of the athlete on the plan according to the motion position, and calculating the athletic performance.
Description
Technical Field
The present document relates to the field of computer identification technologies, and in particular, to a serpentine running motion detection method, apparatus, device, and storage medium.
Background
The snake running is a running motion in an S shape around the cross-arranged targets, belongs to an important examination item in military examination, and athletes encircle the inner side of the targets to the outer side of the targets according to an S-shaped curve, run to the farthest targets and then return to the end point around each target according to the S-shaped curve to finish a round of snake running.
In the related technology, the artificial judgment method in the snake-shaped running detection needs additional staff to assist in calculating the athletic performance and judging the illegal behaviors, so that the degree of automation is low; the infrared determination method needs to detect by means of an infrared sensor, has high hardware cost, and can only record key movement information. In recent years, more intelligent visual judgment methods are often used, namely, a serpentine running process is detected through visual analysis of videos, but the visual judgment methods have the following defects: the inverted rod and the leakage rod in the movement process are difficult to identify, and the inverted rod and the leakage rod are easy to be interfered by the outside.
By combining the analysis of the development status in the technical field, the technical proposal in the prior art lacks of a serpentine running motion detection method, a device, equipment and a storage medium which can eliminate internal and external interferences and judge the rod reversing and rod leakage behaviors.
Disclosure of Invention
The invention aims to provide a serpentine running motion detection method, a serpentine running motion detection device, serpentine running motion detection equipment and a storage medium, and aims to solve the problems in the prior art.
According to a first aspect of an embodiment of the present invention, there is provided a serpentine running motion detection method, including:
Identifying a target in a sports field by adopting a pre-trained target identification model, converting a field plane coordinate through perspective transformation according to a space position identified by the target to obtain a plane diagram corresponding to the field, calculating the range of an in-field area and an out-field area based on the plane diagram, and determining the plane coordinate of the target, wherein the in-field area comprises: a motion zone and a buffer zone;
Identifying the motion information in the sports field by adopting a target identification model, determining the athlete, determining the relationship between the human pole in the motion range of the motion area and the buffer area corresponding to each marker pole, determining the current motion position and the marker pole state of the athlete, and judging the correctness of the relationship between the human pole according to the motion position; forming a motion sequence through a correct human pole relation, judging motion behaviors in each motion range based on the motion sequence and the marker pole state, and performing visual display;
And drawing the motion trail of the athlete on the plan according to the motion position, and calculating the athletic performance.
According to a second aspect of an embodiment of the present invention, there is provided a serpentine running motion detection device comprising:
The area determining module is used for identifying the marker post in the sports ground by adopting a pre-trained target identification model, converting the plane coordinates of the field through perspective transformation according to the identified space position of the marker post, obtaining a plane diagram corresponding to the field, calculating the range of an in-field area and an out-field area based on the plane diagram, and determining the plane coordinates of the marker post, wherein the in-field area comprises: a motion zone and a buffer zone;
The motion behavior judging module is used for identifying motion information in a sport field by adopting a target identification model, determining a player, determining a person pole relation in a motion range of a motion area and a buffer area corresponding to each marker pole, determining the current motion position and the marker pole state of the player, and judging the correctness of the person pole relation according to the motion position; forming a motion sequence through a correct human pole relation, judging motion behaviors in each motion range based on the motion sequence and the marker pole state, and performing visual display;
And the achievement calculating module is used for drawing the motion trail of the athlete on the plan according to the motion position and calculating the athletic achievement.
According to a third aspect of an embodiment of the present invention, there is provided an electronic apparatus including: a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed by the processor, performs the steps of the serpentine running motion detection method as provided in the first aspect of the present disclosure.
According to a fourth aspect of embodiments of the present invention, there is provided a computer-readable storage medium having stored thereon a program for implementing information transfer, which when executed by a processor, implements the steps of the serpentine running motion detection method provided in the first aspect of the present disclosure.
The technical scheme provided by the embodiment of the invention has the following beneficial effects: dividing the sports ground into an intra-field area and an off-field area, and dividing the movement range corresponding to each marker post in the intra-field area, so that external interference outside the intra-field area and self-interference of other marker posts are avoided; and judging the correctness of the human-bar relation recognition according to the movement position, so that the snake-like running vision recognition is more accurate.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
For a clearer description of one or more embodiments of the present description or of the solutions of the prior art, the drawings that are necessary for the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description that follow are only some of the embodiments described in the description, from which, for a person skilled in the art, other drawings can be obtained without inventive faculty.
FIG. 1 is a flow chart of a serpentine motion detection method according to an embodiment of the present invention;
FIG. 2 is a schematic drawing of a plan view of a trace of an embodiment of the present invention;
FIG. 3 is a schematic diagram of a detection framework of an embodiment of the present invention;
FIG. 4 is a schematic diagram of a serpentine motion detection device according to an embodiment of the present invention;
Fig. 5 is a schematic diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to enable a person skilled in the art to better understand the technical solutions in one or more embodiments of the present specification, the technical solutions in one or more embodiments of the present specification will be clearly and completely described below with reference to the drawings in one or more embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one or more embodiments of the present disclosure without inventive faculty, are intended to be within the scope of the present disclosure.
Method embodiment
According to an embodiment of the present invention, there is provided a method for detecting a serpentine running motion, and fig. 1 is a flowchart of the method for detecting a serpentine running motion according to the embodiment of the present invention, as shown in fig. 1, where the method for detecting a serpentine running motion according to the embodiment of the present invention specifically includes:
In step S110, a pre-trained target recognition model is adopted to recognize a target in a sports field, a field plane coordinate is converted through perspective transformation according to a spatial position recognized by the target, a plan corresponding to the field is obtained, a range of an in-field area and an out-field area is calculated based on the plan, and the plane coordinate of the target is determined, wherein the in-field area comprises: a motion zone and a buffer zone. The method specifically comprises the following steps:
in this embodiment, 7 targets and 1 camera are used, the distance between the front and rear of the targets is 10 meters, the distance between the left and right of the targets is 2.5 meters, the targets are arranged in a crossed manner, 4 targets are arranged on the left, 3 targets are arranged on the right, the numbers of the targets are 1 to 7 from the near to the far according to the distance from the camera, and the camera is arranged at a position about 5 meters from the starting line.
The method comprises the steps of determining a rectangle surrounded by all the marker posts as a motion area, performing perspective transformation by taking the marker posts 1, 2, 6 and 7 as reference standards, calculating a perspective transformation matrix, converting the matrix of the fence city into an equal proportion area, determining the size of the converted area as 3000 multiplied by 250, determining an annular rectangle formed by a certain length of the periphery of the motion area as a buffer area, determining the annular rectangle formed by 1.5 meters of the periphery of the motion area as the buffer area, correspondingly converting on a plan view, determining the periphery of the buffer area as an off-site area, taking a straight line where the lower bottom edge of the marker post 1 is located as a starting line and a finishing line, and enabling a camera to annotate the motions of pedestrians in the buffer area and the motion area.
In step S120, identifying motion information in the sports field by using a target identification model, determining that pedestrians at the front left of the number 1 marker post are athletes, determining a human pole relationship between the motion area corresponding to each marker post and the motion range of the buffer area, determining the current motion position and the marker post state of the athletes, and judging the correctness of the human pole relationship according to the motion position; and forming a motion sequence through a correct human pole relation, judging motion behaviors in each motion range based on the motion sequence and the marker pole state, and performing visual display. The method specifically comprises the following steps:
And identifying athletes, upright targets, human pole relations, falling targets and targets which have fallen in the field by adopting a target identification model, wherein the target identification model is a YOLOv model which is trained in advance through field training videos.
Establishing a virtual dividing line through a median line of the vertical distance between adjacent targets, dividing a movement range corresponding to each target through the virtual dividing line, identifying the relationship between a sportsman and the targets in the movement range, and eliminating the interference of other targets; wherein, the human pole relationship includes going to approach the pole, going to parallel with the pole, going to away from the pole, return to approach the pole, return to parallel with the pole, return to away from the pole, and return to junction behind the pole.
The current movement position of the athlete is screened from the identified pedestrian positions by combining the movement position of the athlete at the previous moment through a pedestrian tracking algorithm, so that the current movement position and the movement position at the previous moment are ensured to be generated by the same athlete in the movement process, and the spatial position information of the athlete in a movement area or a buffer area is determined according to the movement position; and (3) eliminating the human pole relation obtained by other recognition targets which are not matched with the space position information as incorrect redundant information, for example, the recognized human pole relation is parallel to the marker pole 4, the movement position of the athlete is in a buffer zone of the movement range of the marker pole 4, and if the movement position of the athlete is not actually in a movement zone corresponding to the marker pole 4 or in a zone corresponding to other marker poles, judging that the human pole relation is obtained by matching other recognition targets, and eliminating the human pole relation as redundant information.
Constructing a motion sequence according to the correct human pole relation, and judging whether the motion behavior corresponding to the motion sequence is normal according to the motion sequence and the marker pole state by combining with a predefined sequence rule; if the motion sequence in the previous motion range is not completed, judging that the rod leakage is caused; if the target recognition model recognizes that the target is in the falling state or has fallen, judging that the target is in the falling state;
The sequence rule comprises that sequences in the motion range of the starting point marker post sequentially finish the going-off approaching rod, the going-off being parallel to the rod and the going-off being far away from the rod; sequentially completing the sequence of going to approach the rod, going to be parallel to the rod, going to return to the junction behind the rod, returning to be parallel to the rod and returning to be far away from the rod in the motion range of the furthest marker post; sequence going-off in the range of motion of the rest of the middle marker posts sequentially completes going-off approaching rods, going-off is parallel to the rods, going-off is far away from the rods and return approaching rods, and return is sequentially completed in parallel with the rods and return is far away from the rods.
In step S130, the athletic performance is calculated by drawing the athletic track of the athlete on the plan view according to the athletic position. The method specifically comprises the following steps:
Converting the motion position information in the video frame into plane coordinates, and forming a series of plane coordinates on a plane graph by drawing software to form a motion track of the athlete, wherein OpenCV software is used in the embodiment, as shown in fig. 2, fig. 2 is a schematic diagram of the plane graph drawing track of the embodiment of the present invention, and the plane graph of the athlete track of the embodiment is shown.
If the rod reversing behavior is identified in the motion process, not calculating the score, otherwise, calculating the motion score according to the starting frame ID, the impulse frame ID and the frame rate identified by the equipment, and calculating the motion score by using a formula 1:
sports score= (impulse frame ID-starting frame ID)/frame rate formula 1;
The leakage rod and the falling rod in the movement process are independently displayed, and whether the leakage rod in the movement process affects the effectiveness of the movement result is determined according to actual conditions.
The above technical solutions of the embodiments of the present invention are illustrated with reference to the following drawings.
FIG. 3 is a schematic diagram of a detection framework according to an embodiment of the present invention, as shown in FIG. 3, illustrating the complete design process of serpentine running motion detection, including pre-deployment of a venue, pre-training of a target recognition model, and serpentine running motion detection during exercise.
In summary, aiming at the problems existing in the current situation, the serpentine running motion detection method of the invention divides a sports ground into an inner field area and an outer field area, and divides the motion range corresponding to each marker post in the inner field area, wherein the inner field area comprises a buffer area and a motion area, so that external interference of external pedestrians or objects and self-interference of other marker posts in the inner field area are avoided; judging whether the snakelike running movement behavior is complete or not through the human pole relation, timely finding out the missing pole behavior, judging the correctness of the human pole relation according to the movement position, obtaining the current movement position of the athlete according to the position of the previous moment, ensuring that the identified athlete is unique, eliminating the human pole relation which does not accord with the athlete and the current marker pole position as abnormal data, improving the accuracy of the human pole relation identification, and enabling the snakelike running visual identification to be more accurate; the motion score is obtained by dividing the index difference between the video frame when the line is punched and the video frame when the line is started by the video frame frequency, so that the calculation accuracy is higher.
Device embodiment
According to an embodiment of the present invention, there is provided a method for detecting a serpentine running motion, and fig. 4 is a flowchart of the method for detecting a serpentine running motion according to the embodiment of the present invention, as shown in fig. 4, where the method for detecting a serpentine running motion according to the embodiment of the present invention specifically includes:
The area determining module 40 is configured to identify a target in the sports field by using a pre-trained target identification model, convert the coordinates of the ground plane by perspective transformation according to the identified spatial position of the target, obtain a plan corresponding to the field, calculate the range of the area in the field and the area outside the field based on the plan, and determine the coordinates of the plane of the target, where the area in the field includes: a motion zone and a buffer zone. The method is particularly used for:
The rectangle surrounded by all the targets is determined as a motion area, an annular rectangle formed by a certain length of the periphery of the motion area is determined as a buffer area, the periphery of the buffer area is determined as an outer field area, and a straight line where the motion area is close to the bottom edge of the camera is taken as a starting line and a finishing line.
The athletic performance judging module 42 is configured to identify athletic information in the athletic field by using the target identification model, determine a player, determine a person-pole relationship in a motion range of the motion area and the buffer area corresponding to each target, determine a current motion position and a target state of the player, and judge correctness of the person-pole relationship according to the motion position; and forming a motion sequence through a correct human pole relation, judging motion behaviors in each motion range based on the motion sequence and the marker pole state, and performing visual display. The method is particularly used for:
and identifying the athlete, the upright marker post, the human pole relation, the marker post which is falling and the marker post which is already falling in the field by adopting a target identification model, wherein the target identification model is a YOLOv model.
Establishing a virtual dividing line through a median line of the vertical distance between adjacent targets, dividing a movement range corresponding to each target through the virtual dividing line, and identifying the person-pole relationship between the athlete and the targets in the movement range; wherein, the human pole relationship includes going to approach the pole, going to parallel with the pole, going to away from the pole, return to approach the pole, return to parallel with the pole, return to away from the pole, and return to junction behind the pole.
Selecting the current movement position of the athlete from the identified pedestrian positions by combining the movement position of the athlete at the previous moment through a pedestrian tracking algorithm, and determining the spatial position information of the athlete in the movement area or the buffer area according to the movement position; and eliminating the human pole relation obtained by other recognition targets which are not matched with the space position information as incorrect redundant information.
Constructing a motion sequence according to the correct human pole relation, and judging whether the motion behavior corresponding to the motion sequence is normal according to the motion sequence and the marker pole state by combining with a predefined sequence rule; if the motion sequence in the previous motion range is not completed, judging that the rod leakage is caused; if the target recognition model recognizes that the target is in the falling state or has fallen, judging that the target is in the falling state;
The sequence rule comprises that sequences in the motion range of the starting point marker post sequentially finish the going-off approaching rod, the going-off being parallel to the rod and the going-off being far away from the rod; sequentially completing the sequence of going to approach the rod, going to be parallel to the rod, going to return to the junction behind the rod, returning to be parallel to the rod and returning to be far away from the rod in the motion range of the furthest marker post; sequence going-off in the range of motion of the rest of the middle marker posts sequentially completes going-off approaching rods, going-off is parallel to the rods, going-off is far away from the rods and return approaching rods, and return is sequentially completed in parallel with the rods and return is far away from the rods.
The achievement calculating module 44 is configured to draw a motion trail of the athlete on the plan view according to the motion position, and calculate the athletic achievement. The method is particularly used for:
If the rod reversing behavior is identified in the motion process, not calculating the score, otherwise, calculating the motion score according to the starting frame ID, the impulse frame ID and the frame rate identified by the equipment, and calculating the motion score by using a formula 1:
sports score= (impulse frame ID-starting frame ID)/frame rate formula 1.
In summary, aiming at the problems existing in the current situation, the serpentine running motion detection device divides a sports ground into an inner field area and an outer field area, and divides a motion range corresponding to each marker post in the inner field area, wherein the inner field area comprises a buffer area and a motion area, so that external interference of external pedestrians or objects and self-interference of other marker posts in the inner field area are avoided; judging whether the snakelike running movement behavior is complete or not through the human pole relation, timely finding out the missing pole behavior, judging the correctness of the human pole relation according to the movement position, obtaining the current movement position of the athlete according to the position of the previous moment, ensuring that the identified athlete is unique, eliminating the human pole relation which does not accord with the athlete and the current marker pole position as abnormal data, improving the accuracy of the human pole relation identification, and enabling the snakelike running visual identification to be more accurate; the motion score is obtained by dividing the index difference between the video frame when the line is punched and the video frame when the line is started by the video frame frequency, so that the calculation accuracy is higher.
Electronic device embodiment
Fig. 5 is a schematic diagram of an electronic device according to an embodiment of the invention. The electronic device 500 may include at least one processor 510 and memory 520. Processor 510 may execute instructions stored in memory 520. The processor 510 is communicatively coupled to the memory 520 via a data bus. In addition to memory 520, processor 510 may be communicatively coupled with input device 530, output device 540, and communication device 550 via a data bus.
The processor 510 may be any conventional processor, such as a commercially available CPU. The processor may also include, for example, an image processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable GATE ARRAY, FPGA), a System On Chip (SOC), an Application SPECIFIC INTEGRATED Circuit (ASIC), or a combination thereof.
The memory 520 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
In the embodiment of the present disclosure, the memory 520 stores executable instructions, and the processor 510 may read the executable instructions from the memory 520 and execute the instructions to implement all or part of the steps of the serpentine running motion detection method according to any one of the above-described exemplary embodiments.
Computer-readable storage medium embodiments
In addition to the methods and apparatus described above, exemplary embodiments of the present disclosure may also be a computer program product or a computer readable storage medium storing the computer program product, the computer program product including computer program instructions executable by a processor to implement all or part of the steps described in the serpentine running motion detection method of any of the exemplary embodiments described above.
The computer program product may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages, as well as scripting languages (e.g., python). The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
A computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the readable storage medium include: a Static Random Access Memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic or optical disk, or any suitable combination of the foregoing having one or more electrical conductors.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (8)
1. A serpentine running motion detection method, comprising:
Identifying a target in a sports field by adopting a pre-trained target identification model, converting a field plane coordinate through perspective transformation according to a space position identified by the target to obtain a plane diagram corresponding to the field, calculating the range of an in-field area and an out-field area based on the plane diagram, and determining the plane coordinate of the target, wherein the in-field area comprises: a motion zone and a buffer zone;
Identifying the motion information in the sports field by adopting the target identification model, determining the athlete, determining the human pole relation in the motion range of each marker post corresponding to the motion area and the buffer area, determining the current motion position and the marker post state of the athlete, and judging the correctness of the human pole relation according to the motion position; forming a motion sequence through a correct human pole relation, judging motion behaviors in each motion range based on the motion sequence and the marker pole state, and performing visual display, wherein the method specifically comprises the following steps of:
Establishing a virtual dividing line through a median line of the vertical distance between adjacent targets, dividing a movement range corresponding to each target through the virtual dividing line, and identifying the person-pole relationship between the athlete and the targets in the movement range; wherein the human pole relationship comprises a forward travel approaching pole, a forward travel parallel to the pole, a forward travel away from the pole, a return travel approaching pole, a return travel parallel to the pole, a return travel away from the pole and a return travel junction behind the pole;
Screening the current movement position of the athlete from the identified pedestrian positions by a pedestrian tracking algorithm and combining the movement position of the athlete at the previous moment, and determining the spatial position information of the athlete in a movement area or a buffer area according to the movement position; the person-pole relation obtained by other recognition targets which are not matched with the space position information is taken as incorrect redundant information to be removed;
and drawing the motion trail of the athlete on the plan according to the motion position, and calculating the athletic performance.
2. The method according to claim 1, wherein the identifying the targets in the sports field by using the pre-trained target identification model, converting the coordinates of the ground plane by perspective transformation according to the identified spatial positions of the targets, and obtaining the plan corresponding to the field specifically includes:
The method comprises the steps of determining a rectangle surrounded by all the targets as a motion area, determining an annular rectangle formed by a certain length of the periphery of the motion area as a buffer area, determining the periphery of the buffer area as an outer field area, and taking a straight line where the motion area is close to the bottom edge of a camera as a starting line and a finishing line.
3. The method according to claim 1, wherein the identifying the motion information in the playing field using the object identification model specifically comprises:
And identifying the athlete, the upright marker post, the human pole relation, the marker post which is falling and the marker post which is already falling in the field by adopting the target identification model, wherein the target identification model is a YOLOv model.
4. The method according to claim 1, wherein the forming a motion sequence by the correct person-pole relationship, determining motion behaviors in each motion range based on the motion sequence and the target state, and visually displaying specifically includes:
Constructing a motion sequence according to a correct human pole relation, and judging whether the motion behavior corresponding to the motion sequence is normal according to the motion sequence and the marker pole state by combining with a predefined sequence rule; if the motion sequence in the previous motion range is not completed, judging that the rod leakage is caused; if the target recognition model recognizes that the target is in the falling state or has fallen, judging that the target is in the falling state;
The sequence rule comprises that sequences in the motion range of the starting point marker post sequentially finish the going-off approaching rod, the going-off being parallel to the rod and the going-off being far away from the rod; sequentially completing the sequence of going to approach the rod, going to be parallel to the rod, going to return to the junction behind the rod, returning to be parallel to the rod and returning to be far away from the rod in the motion range of the furthest marker post; sequence going-off in the range of motion of the rest of the middle marker posts sequentially completes going-off approaching rods, going-off is parallel to the rods, going-off is far away from the rods and return approaching rods, and return is sequentially completed in parallel with the rods and return is far away from the rods.
5. The method according to claim 1, characterized in that said calculating the athletic performance comprises in particular:
If the rod reversing behavior is identified in the motion process, not calculating the score, otherwise, calculating the motion score according to the starting frame ID, the impulse frame ID and the frame rate identified by the equipment, and calculating the motion score by using a formula 1:
sports score= (impulse frame ID-starting frame ID)/frame rate formula 1.
6. A serpentine running motion detection device, comprising:
The area determining module is used for identifying the marker post in the sports ground by adopting a pre-trained target identification model, converting the plane coordinates of the field through perspective transformation according to the identified space position of the marker post, obtaining a plane diagram corresponding to the field, calculating the range of an in-field area and an out-field area based on the plane diagram, and determining the plane coordinates of the marker post, wherein the in-field area comprises: a motion zone and a buffer zone;
The motion behavior judging module is used for identifying motion information in a sport field by adopting the target identification model, determining a player, determining a person pole relation in a motion range of each marker pole corresponding to the motion area and the buffer area, determining a current motion position and a marker pole state of the player, and judging the correctness of the person pole relation according to the motion position; forming a motion sequence through a correct human pole relation, judging motion behaviors in each motion range based on the motion sequence and the marker pole state, and performing visual display, wherein the method is particularly used for:
Establishing a virtual dividing line through a median line of the vertical distance between adjacent targets, dividing a movement range corresponding to each target through the virtual dividing line, and identifying the person-pole relationship between the athlete and the targets in the movement range; wherein the human pole relationship comprises a forward travel approaching pole, a forward travel parallel to the pole, a forward travel away from the pole, a return travel approaching pole, a return travel parallel to the pole, a return travel away from the pole and a return travel junction behind the pole;
Screening the current movement position of the athlete from the identified pedestrian positions by a pedestrian tracking algorithm and combining the movement position of the athlete at the previous moment, and determining the spatial position information of the athlete in a movement area or a buffer area according to the movement position; the person-pole relation obtained by other recognition targets which are not matched with the space position information is taken as incorrect redundant information to be removed;
And the achievement calculating module is used for drawing the motion trail of the athlete on the plan according to the motion position and calculating the athletic achievement.
7. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, which when executed by the processor, performs the steps of the serpentine running motion detection method according to any one of claims 1 to 5.
8. A computer readable storage medium, wherein a program for implementing information transfer is stored on the computer readable storage medium, and when the program is executed by a processor, the steps of the serpentine running motion detection method according to any one of claims 1 to 5 are implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311336864.6A CN117333945B (en) | 2023-10-16 | 2023-10-16 | Snake running motion detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311336864.6A CN117333945B (en) | 2023-10-16 | 2023-10-16 | Snake running motion detection method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117333945A CN117333945A (en) | 2024-01-02 |
| CN117333945B true CN117333945B (en) | 2024-06-18 |
Family
ID=89292893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311336864.6A Active CN117333945B (en) | 2023-10-16 | 2023-10-16 | Snake running motion detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117333945B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118172389B (en) * | 2024-05-14 | 2024-07-26 | 山东科技大学 | Short-distance track monitoring system and method based on multi-target tracking across cameras |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114037728A (en) * | 2021-10-15 | 2022-02-11 | 江苏爱好人工智能科技有限公司 | Snake-shaped running track judgment method based on computer vision |
| CN114972475A (en) * | 2022-05-17 | 2022-08-30 | 泰山体育产业集团有限公司 | Snake-shaped running assessment method and implementation device thereof |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10127563B2 (en) * | 2011-09-15 | 2018-11-13 | Stephan HEATH | System and method for providing sports and sporting events related social/geo/promo link promotional data sets for end user display of interactive ad links, promotions and sale of products, goods, gambling and/or services integrated with 3D spatial geomapping, company and local information for selected worldwide locations and social networking |
| EP3622646B1 (en) * | 2017-05-08 | 2020-10-21 | Coherent Logix, Inc. | Enhanced polarization weighting to enable scalability in polar code bit distribution |
| US20180357870A1 (en) * | 2017-06-07 | 2018-12-13 | Amazon Technologies, Inc. | Behavior-aware security systems and associated methods |
| CN110711369A (en) * | 2019-11-11 | 2020-01-21 | 福建（泉州）哈工大工程技术研究院 | Winding rod training and examination system and examination data acquisition method thereof |
| US11710317B2 (en) * | 2020-03-04 | 2023-07-25 | Recruiting Analytics LLC | Systems, methods, and computer-program products for assessing athletic ability and generating performance data |
| US11450051B2 (en) * | 2020-11-18 | 2022-09-20 | Snap Inc. | Personalized avatar real-time motion capture |
| CN114445945A (en) * | 2022-02-12 | 2022-05-06 | 钟蕾 | A place intelligent system for sports ground |
| WO2023158834A1 (en) * | 2022-02-18 | 2023-08-24 | The Johns Hopkins University | Systems and methods for detection and localization of foreign body objects |
| CN115311681A (en) * | 2022-07-15 | 2022-11-08 | 恒鸿达科技有限公司 | Football dribbling rod-winding test method, device and equipment based on vision technology |
| CN116485236A (en) * | 2023-03-27 | 2023-07-25 | 中国消防救援学院 | Intelligent monitoring and early warning method and system for firefighter occupational training |
-
2023
- 2023-10-16 CN CN202311336864.6A patent/CN117333945B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114037728A (en) * | 2021-10-15 | 2022-02-11 | 江苏爱好人工智能科技有限公司 | Snake-shaped running track judgment method based on computer vision |
| CN114972475A (en) * | 2022-05-17 | 2022-08-30 | 泰山体育产业集团有限公司 | Snake-shaped running assessment method and implementation device thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117333945A (en) | 2024-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hu et al. | Monocular quasi-dense 3d object tracking | |
| CN111401201B (en) | Aerial image multi-scale target detection method based on spatial pyramid attention drive | |
| Pang et al. | CLOCs: Camera-LiDAR object candidates fusion for 3D object detection | |
| KR102261061B1 (en) | Systems and methods for detecting a point of interest change using a convolutional neural network | |
| CN111696128B (en) | High-speed multi-target detection tracking and target image optimization method and storage medium | |
| CN110706259B (en) | Space constraint-based cross-shot tracking method and device for suspicious people | |
| Milan et al. | Continuous energy minimization for multitarget tracking | |
| RU2628155C2 (en) | Device, method and computer program for reconstruction of object motion | |
| Milan et al. | Challenges of ground truth evaluation of multi-target tracking | |
| CN117333945B (en) | Snake running motion detection method, device, equipment and storage medium | |
| Xiong et al. | LXL: LiDAR excluded lean 3D object detection with 4D imaging radar and camera fusion | |
| CN106203418A (en) | A kind of method and device of car plate detection | |
| Zheng et al. | Cows' legs tracking and lameness detection in dairy cattle using video analysis and Siamese neural networks | |
| CN106446002A (en) | Moving target-based video retrieval method for track in map | |
| CN104318559A (en) | Quick feature point detecting method for video image matching | |
| CN112634368A (en) | Method and device for generating space and OR graph model of scene target and electronic equipment | |
| CN102944180B (en) | Table tennis ball tossing height detecting system and method based on image processing | |
| CN115797736A (en) | Method, device, equipment and medium for training target detection model and target detection | |
| Yan et al. | Multicamera pedestrian detection using logic minimization | |
| CN109697727A (en) | Method for tracking target, system and storage medium based on correlation filtering and metric learning | |
| CN114842439A (en) | Cross-perception-device vehicle identification method and device, electronic device and storage medium | |
| CA2433885A1 (en) | System and method for the measurement of the relative position of an object with respect to a point of reference | |
| Tan et al. | Efficient lane detection system based on monocular camera | |
| CN113689475A (en) | Cross-border head trajectory tracking method, equipment and storage medium | |
| CN113470073A (en) | Animal center tracking method based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |